Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    author biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fans
    -0.07
    Absolutely
    -0.07
     Conte
    -0.06
    usra
    -0.06
    Customers
    -0.06
     Somebody
    -0.06
     celebrated
    -0.06
    _numpy
    -0.06
    Persistence
    -0.06
     savvy
    -0.06
    POSITIVE LOGITS
    ι
    0.07
    pections
    0.07
     signin
    0.07
    ainted
    0.06
    .Delay
    0.06
     nell
    0.06
    ('',
    0.06
    .Man
    0.06
    (xi
    0.06
    ных
    0.06
    Act Density 0.047%

    No Known Activations